Model key: sentiment

The sentiment analyzer is trained to detect the sentiment of a text. It can detect positive, negative and neutral sentiment.

Sentiment analysis is a very subjective task. The model is trained on a large dataset, but positive and negative might mean something else in your context.

Response Example:
{
  "label": "NEGATIVE",
  "score": 0.999568,
  "label_scores": {
    "NEGATIVE": 0.999568,
    "NEUTRAL": 0,
    "POSITIVE": 0
  }
}

​
Labels

LabelDescription
NEGATIVENegative sentiment
POSITIVEPositive sentiment
NEUTRAL

​
Supported languages

This model has been tested in the following languages:

  • English en
  • ... (other languages still to be tested)

The model also works with other launguages we haven't tested. Feel free to try it on launguages that are not listed above and provide us with feedback.

​
Limitations

This model has a 1.000 characters per request limit. You can still post texts with more than 1.000 characters, but it will increase the quota usage. For example, a 1.500 characters text will count as 2 requests.

Model key: sentiment

The sentiment analyzer is trained to detect the sentiment of a text. It can detect positive, negative and neutral sentiment.

Sentiment analysis is a very subjective task. The model is trained on a large dataset, but positive and negative might mean something else in your context.

Response Example:
{
  "label": "NEGATIVE",
  "score": 0.999568,
  "label_scores": {
    "NEGATIVE": 0.999568,
    "NEUTRAL": 0,
    "POSITIVE": 0
  }
}

​
Labels

LabelDescription
NEGATIVENegative sentiment
POSITIVEPositive sentiment
NEUTRAL

​
Supported languages

This model has been tested in the following languages:

  • English en
  • ... (other languages still to be tested)

The model also works with other launguages we haven't tested. Feel free to try it on launguages that are not listed above and provide us with feedback.

​
Limitations

This model has a 1.000 characters per request limit. You can still post texts with more than 1.000 characters, but it will increase the quota usage. For example, a 1.500 characters text will count as 2 requests.